I am interested in applying Bayesian additive regression trees (BART) for classification analysis of gene expression data. I am relatively new to R (and Bioconductor packages) and I am unable to find some code or vignette that I can use to learn from. I will be thankful if someone can point me in a good direction.
$\begingroup$
$\endgroup$
0
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
2
I would suggest looking at the BayesTree package, from CRAN. I have no experience with it, so I cannot say if there are better option from there. Try looking at the Machine Learning Task View, or directly through www.rseek.org.
I don't know anything approaching in Bioconductor, but if the above package suits your needs I guess you won't have any problem with gene expression data. I know the CMA package offer a full-featured pipeline for supervised classification (see e.g., CMA - A comprehensive Bioconductor package for super- vised classification with high dimensional data, by Slawski et al.). Maybe you can plug BART method in addition to the available methods?
-
1$\begingroup$ BayesTree is done by the inventors of BART, I believe. But the
bartMachinepackage looks like a better option to me. (The only downside is it requires Java and interfaces to it via therJavapackage, which might complicate things if your machine doesn't have Java installed.) $\endgroup$– WayneCommented Mar 11, 2015 at 22:02 -
$\begingroup$ The
BARTanddbartspackages are reasonable alternatives nowadays. $\endgroup$ Commented Dec 17, 2022 at 3:41